Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125360
    Prev
    Next
    INDEX
    Explanations

    portion

    np_max-act · gemini-2.0-flash

    The neuron is triggered by references to controlling or measuring food portions (e.g. “portion,” “sizes,” “measuring cups,” “serving sizes”), i.e. portion‐control guidance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strncmp
    -0.06
    arc
    -0.06
     listBox
    -0.06
     cane
    -0.06
     sqlite
    -0.06
    remarks
    -0.06
    CLUSION
    -0.06
     trunk
    -0.06
    ��作
    -0.06
    .Box
    -0.06
    POSITIVE LOGITS
     shaping
    0.06
     Costs
    0.06
    について
    0.06
    Href
    0.06
    orph
    0.06
    ecom
    0.06
     tossing
    0.06
     kön
    0.06
    べき
    0.06
    Setter
    0.06
    Activations Density 0.004%

    No Known Activations